LibreChat logo

Run LibreChat on Inkling NVFP4

by LibreChatChat applibrechat.ai

LibreChat is the leading open-source AI chat platform, a self-hosted ChatGPT alternative with multi-model chat, agents, file handling, and search. Custom endpoints are a headline feature: one block in librechat.yaml adds any OpenAI-compatible provider. Point it at Opper and your whole workspace chats across 700+ models on one key, with a choice of EU or US inference behind it.

RunLibreChat logoLibreChatonin

Connect LibreChat to Inkling NVFP4

Set up with agents

Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.

Get your API key

Where you can run it

Inkling NVFP4 runs on the routes below. Route only to EU providers when your data has to stay in Europe.

ProviderRegionZero data retentionTrainingInputOutput
ModalMultiNo (opt-in)$1.20$5.00

The model

by Thinking Machines

Inkling NVFP4 is the 4-bit quantized build of Thinking Machines Lab's 975B open-weight multimodal Mixture-of-Experts, 41B active, with text, image and audio input and a 1M-token context.

Available on

Pricing from$1.20/ 1M input$5.00/ 1M output1Mcontext

Privacy

ZDR
Training
No (opt-in)
Region
Multi

More apps on Opper

Run LibreChat on Inkling NVFP4

One key, 700+ models, a choice of region, and zero data retention. Switch the model behind your app without changing your workflow.

Get startedView Documentation